Atlas record: https://www.aitimeline.dev/en/events/evt-0046/
Research · April 1980
Kunihiko Fukushima described a multilayer network for pattern recognition that tolerates shifts in position.
Its local features and pooling layers precede the convolutional networks that later became the basis of computer vision.
The network was trained by self-organisation rather than by backpropagation.
Biological Cybernetics · Published April 1980
Springer-Verlag (Biological Cybernetics), copy hosted by the Redwood Center for Theoretical Neuroscience · Published 1980
The 1980 neocognitron is the same author's direct continuation of this work.
Fukushima writes that the neocognitron, once self-organised, has a structure like Hubel and Wiesel's hierarchy model: its S-cells resemble simple cells and its C-cells complex ones.
Convolution and weight sharing come from the neocognitron, but here they are trained by gradient.
Both recognise images through layers of local features; the later one ran on much larger data and on GPUs.